Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add OneWave-AI/claude-skills --skill claude-design-criticgit clone --depth 1 https://github.com/OneWave-AI/claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/onewave-ai/claude-skills/claude-design-critic)<a href="https://agentmods.dev/skills/onewave-ai/claude-skills/claude-design-critic"><img src="https://agentmods.dev/badge/skills/onewave-ai/claude-skills/claude-design-critic/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/onewave-ai/claude-skills/claude-design-critic"><img src="https://agentmods.dev/badge/skills/onewave-ai/claude-skills/claude-design-critic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 68 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00091 | $0.00991 |
| Opus 5 | $0.00046 | $0.00495 |
| Sonnet 5 | $0.00018 | $0.00198 |
| Haiku 4.5 | $0.00009 | $0.00099 |
Grade A, and why
claude-design-critic scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Design Critic
Some sites are technically fine and still scream "an AI made this in one shot." This skill names exactly why and tells you what to change. It reviews the design and the copy, because generated-looking text gives a build away as fast as a centered hero and a purple gradient.
Use it as the finishing pass on claude-landing-composer output, on any vibe-coded frontend, or on a live site that feels generic. It pairs with the design tokens from claude-design-system-architect (audit against them when they exist).
Step 1 — Take in the target
A URL (WebFetch + screenshot), a local project (read the components/styles), or pasted code. Establish: what is this page for, who's the audience, and what's the one action it wants? A critique without the goal is just opinion.
Step 2 — Audit across dimensions
Go dimension by dimension and flag concrete instances, not vibes:
Layout & composition
- Every section a centered stack? Three-identical-cards reflex? Predictable hero → cards → CTA with no rhythm? Symmetry where asymmetry would feel crafted? Cramped or uniform whitespace?
Color
- Purple or default-AI gradients (the dead giveaway). Too many competing accents. Off-brand or arbitrary hexes not mapped to tokens. Contrast failures (check AA).
Type
- Default system sans at 2–3 sizes. No real modular scale. Weak hierarchy. Generic pairing. Line length / line-height that reads like a default.
Spacing & detail
- Uniform padding everywhere. No optical adjustments. Borders/shadows that are all identical or all heavy.
Motion
- The same fade-up on every element. Motion that decorates instead of directs.
prefers-reduced-motionignored.
Iconography & assets
- Emoji used as UI (replace with Lucide/Heroicons). Generic stock imagery. Placeholder logos left in.
Copy (review this as hard as the design)
- AI tells: "elevate", "unlock", "seamless", "empower", "in today's fast-paced world", "we're thrilled to", "the power of", relentless em-dashes, every sentence a tricolon.
- Generic value props ("the best way to X"), hedged language, "Learn More" buttons, "Welcome to {Product}" heroes, filler microcopy.
- Flag the exact lines and rewrite the worst offenders.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 78 lines · 91 tokens per session scan A 7a7c366b4659
claude-design-critic is a skill published in the GitHub repository OneWave-AI/claude-skills (291 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 991 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
information-architecture
Design the structure of a website or product including sitemap, navigation, URL structure, content types, taxonomy, and labeling. Use this skill whenever the user asks to plan a sitemap, design navigation, structure URLs, define content types, build taxonomies, design site search, or organize content at the system…
journey-mapping
Build customer journey maps and service blueprints that visualize the end-to-end user experience including touchpoints, emotions, friction, and underlying systems. Use this skill whenever the user wants to map a customer journey, build a service blueprint, identify friction across an experience, align teams on the…
usability-testing
Plan and run usability tests on existing or prototype designs including test design, task scripts, moderation, observation, and findings synthesis. Use this skill whenever the user wants to test usability, run a moderated test, run an unmoderated test, validate a design, find usability issues, or improve task…
brand-style-guide
Build or audit a comprehensive brand style guide that documents the full brand system including story, logo system, color, typography, imagery, voice, applications, and dos/don'ts. Use this skill whenever the user wants to create brand guidelines, document an existing brand, build a brand book, audit an existing style…
visual-qa
Runs rigorous visual QA across web, terminal, and paginated surfaces with screenshot evidence and a verdict. Use for any UI build or change, or when asked whether a page, component, or TUI looks right.
frontend
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.